// the find
susanli2016/Data-Analysis-with-R
Using gglot2, tidyr, dplyr, ggmap, choroplethr, shiny, logistic regression, clustering models and more
A collection of R Markdown exploratory data analysis notebooks from 2016–2018, covering text mining, choropleth mapping, logistic regression, and clustering across public datasets. It's a portfolio repo, not a library — useful for seeing how someone applied tidyverse tools to real problems, not for importing into your own project.
The dataset variety is genuinely good: election finance, marathon results, H-1B petitions, and literary text mining cover a wide range of EDA patterns. The RMarkdown format means you can run any notebook locally and reproduce the output step by step. Covers the full analytics stack — ggplot2 for viz, dplyr/tidyr for wrangling, caret for modeling — so it works as a reference for 'how did they do X'.
Frozen in 2018 and unlikely to run cleanly today — package APIs have shifted, external data URLs (RPubs links, shinyapps.io) may be dead, and none of the notebooks have dependency lockfiles (no renv, no packrat). It's a flat directory of .Rmd files with no shared utilities, so every notebook reinvents basic data-loading and cleaning. The README is just a link list; there's no explanation of methodology choices or what each project actually teaches.